© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18296
    Prev
    Next
    INDEX
    Explanations

    seasonally related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lish
    -0.10
    uter
    -0.09
    sock
    -0.09
     Loves
    -0.09
    件
    -0.09
    wan
    -0.09
     Valk
    -0.09
    eness
    -0.09
    еÑģÑĤво
    -0.09
    iffin
    -0.09
    POSITIVE LOGITS
    ality
    0.23
    ably
    0.18
    ings
    0.17
     finale
    0.17
    ally
    0.15
     opener
    0.13
    -long
    0.12
    als
    0.12
    alties
    0.12
    -ending
    0.12
    Activations Density 0.051%

    No Known Activations